Is Solving Better Than Evaluating GenAI Solutions?

Ethan Dickey, Marios Mertzanidis, Alexandros Psomas (2026) — arXiv:2607.27586 (cs.CY, cs.AI)

📄 Full text (arXiv)

Summary

Randomized A/B crossover study (N=22) in upper-division computing courses comparing solution evaluation/critique tasks against traditional solution generation. Finds that evaluation-centered tasks produce comparable or better learning outcomes, suggesting an effective pedagogical response to the availability of GenAI code generation tools.

The work connects to broader discussions in AI and education around generative-ai, computing-education, student-experience, contributing to our understanding of how generative ai shapes educational practice.

Key Contributions

• Contributes empirical or theoretical advances relevant to the generative-ai domain

• Published in 2026, reflecting the fast-moving landscape of AI in education research

• Engages with questions of stem education and higher ed in educational contexts

Related Pages

• generative-ai

• computing-education

• student-experience

• learning-outcomes

• academic-integrity

Citation

APA: Ethan Dickey, Marios Mertzanidis, Alexandros Psomas (2026). Is Solving Better Than Evaluating GenAI Solutions?. arXiv:2607.27586. cs.CY, cs.AI.